Papers with English-Arabic

2 papers
Generating Image Captions in Arabic using Root-Word Based Recurrent Neural Networks and Deep Neural Networks (N18-4)

Copied to clipboard

Challenge: Existing studies on image caption generation in English focus on Western languages, ignoring Semitic and Middle-Eastern languages like Arabic, Hebrew, Urdu and Persian.
Approach: They propose to leverage the critical dependency of Arabic to generate Arabic captions using root-word based Recurrent Neural Network and Deep Neural networks.
Outcome: The proposed model outperforms English-Arabic translated captions on a dataset from newspapers in the Middle East.
A Discriminative Neural Model for Cross-Lingual Word Alignment (D19-1)

Copied to clipboard

Challenge: a novel word alignment model for machine translation has been developed for a number of languages . explicit word-to-word alignments have largely been lost in neural MT systems .
Approach: They propose a discriminative word alignment model which integrates into a Transformer-based machine translation model.
Outcome: The proposed model performs better on Chinese and Arabic alignments than standard models.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations